A Self-Supervised Multiview Contrastive Learning Network for the Fault Diagnosis of Rotating Machinery Under Limited Annotation Information

The field of rotating machinery has long faced the challenge of limited annotated samples, which significantly affects the performance of neural network models. Most existing methods rely mainly on a few annotated samples for fault diagnosis algorithm design without fully utilizing a large amount of unannotated data in the monitoring phase. To alleviate the effect of limited annotation information, this article proposes a self-supervised multiview contrastive learning network (SMCLN) based on time-frequency analysis. This framework learns from a large number of unlabeled samples and leverages the rich feature information contained in time-frequency images to train a feature extractor with strong generalization capabilities. Given the significant differences between vibration signals and images, this article designs appropriate data augmentation methods. Additionally, a multitask mechanism is introduced by designing a novel loss function, enabling the network to simultaneously handle both matching and prediction tasks. This approach enhances the representational capacity and further improves overall performance. Finally, a simple linear classifier is added and fine-tuned on a small amount of labeled data. Experiments on both public and laboratory datasets demonstrate that our proposed SMCLN can effectively extract valuable feature information and significantly improve classification accuracy under limited annotated datasets.

I. Introduction

With the rapid advancement of sensor technology, the automation and intelligence levels of mechanical equipment have significantly improved, leading to a continuous increase in the volume of monitoring data. This monitoring data not only plays a crucial role in enhancing the operational safety and stability of mechanical equipment but also profoundly influences maintenance and repair strategies [1], [2], [3]. Therefore, data-driven fault diagnosis methods have attracted extensive attention in rotating machinery. By profoundly analyzing and processing massive amounts of monitoring data, these methods can identify and predict equipment faults in real-time, thus optimizing maintenance schedules and significantly improving equipment reliability and lifetime [4], [5].